INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    iken
    -0.75
    wings
    -0.68
    MK
    -0.66
     camoufl
    -0.65
    reb
    -0.65
    Room
    -0.64
    è¦ļéĨĴ
    -0.64
    ür
    -0.63
     tunnels
    -0.62
    apons
    -0.62
    POSITIVE LOGITS
     Greg
    3.42
    Greg
    2.66
     Gregory
    1.76
    greg
    1.59
     Gregg
    1.50
     Geoff
    1.43
     Josh
    1.41
     Gavin
    1.38
     Jeff
    1.32
     Doug
    1.32
    Act Density 0.018%

    No Known Activations